Code for "Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation" (ICML 2026)

Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.

CausalLM

Data, Codes, Materials and things for computational neurobiology project

The official implementation of TinyTrain [ICML '24]

This is a research project to efficiently compress diffusion models, accepted at AAAI 2026.

Code for ICLR26 paper - Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment

The SDK for Jetpac's iOS Deep Belief image recognition framework

Tensor library for machine learning

AirLLM 70B inference with single 4GB GPU

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Learning to use this device. You'll find edge AI applications and useful commands to optimize your Jetson

[TMLR] LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

React Starter Kit built using React Router v7, Clerk, Convex & Polar

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

GGUF Quantization support for native ComfyUI models

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

A curated list of resources for using LLMs to develop more competitive grant applications.

Official inference repo for FLUX.1 models

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters